© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 11299
    Prev
    Next
    INDEX
    Explanations

    phrases related to unity or support

    oai_token-act-pair · gpt-3.5-turbo

    terms related to psychological or social pressures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verend
    -0.79
     Kard
    -0.77
     Ryder
    -0.74
    edly
    -0.74
    Appearances
    -0.72
     Almighty
    -0.71
     Telesc
    -0.70
    Wan
    -0.69
    idently
    -0.68
    enance
    -0.67
    POSITIVE LOGITS
     adaptation
    0.73
     experimentation
    0.63
     bonding
    0.61
     gymn
    0.61
    requ
    0.60
     vein
    0.59
     oper
    0.59
     outfit
    0.58
     palette
    0.58
     fin
    0.58
    Activations Density 0.000%

    No Known Activations